Time-Series Forecasting Method Based on Hierarchical Spatio-Temporal Attention Mechanism
Sensors · 26.06.2025 · 25 (13) · 4001
DOI: 10.3390/s25134001 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 26.06.2025. Verfasst von Zhiguo Xiao und 5 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer Science & Technology, Beijing Institute of Technology, Beijing 100811, China. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 34 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: the Basic Construction Funds within the Budget of Jilin Province in 2024, the 2022 Open Research Project of the National Key Laboratory for Special Vehicle Design and Manufacturing Integration Technology, Science and Technology Development Project of the Education Department of Jilin Province.
Abstract (Originalsprache)
In the field of intelligent decision-making, time-series data collected by sensors serves as the core carrier for interaction between the physical and digital worlds. Accurate analysis is the cornerstone of decision-making in critical scenarios, such as industrial monitoring and intelligent transportation. However, the inherent spatio-temporal coupling characteristics and cross-period long-range dependency of sensor data cause traditional time-series prediction methods to face performance bottlenecks in feature decoupling and multi-scale modeling. This study innovatively proposes a Spatio-Temporal Attention-Enhanced Network (TSEBG). Breaking through traditional structural designs, the model employs a Squeeze-and-Excitation Network (SENet) to reconstruct the convolutional layers of the Temporal Convolutional Network (TCN), strengthening the feature expression of key time steps through dynamic channel weight allocation to address the redundancy issue of traditional causal convolutions in local pattern capture. A Bidirectional Gated Recurrent Unit (BiGRU) variant based on a global attention mechanism is designed, leveraging the collaboration between gating units and attention weights to mine cross-period long-distance dependencies and effectively alleviate the gradient disappearance problem of Recurrent Neural Network (RNN-like) models in multi-scale time-series analysis. A hierarchical feature fusion architecture is constructed to achieve multi-dimensional alignment of local spatial and global temporal features. Through residual connections and the dynamic adjustment of attention weights, hierarchical semantic representations are output. Experiments show that TSEBG outperforms current dominant models in time-series single-step prediction tasks in terms of accuracy and performance, with a cross-dataset R2 standard deviation of only 3.7%, demonstrating excellent generalization stability. It provides a novel theoretical framework for feature decoupling and multi-scale modeling of complex time-series data.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Computer Science & Technology, Beijing Institute of Technology, Beijing 100811, China.
- College of Computer Science and Technology, Changchun University, Changchun 130022, China.
- National Key Laboratory of Special Vehicle Design and Manufacturing Integration Technology, Baotou 014000, China.
ORCID-Profile: Zhiguo Xiao
Förderung
- the Basic Construction Funds within the Budget of Jilin Province in 2024
- the 2022 Open Research Project of the National Key Laboratory for Special Vehicle Design and Manufacturing Integration Technology
- Science and Technology Development Project of the Education Department of Jilin Province
- Basic Construction Funds within the Budget of Jilin Province in 2024
Zitieren
APA
Xiao, Z., Liu, J., Cao, X., Wang, K., Li, D., & Liu, Q. (2025). Time-Series Forecasting Method Based on Hierarchical Spatio-Temporal Attention Mechanism. Sensors, 25(13), 4001. https://doi.org/10.3390/s25134001
Vancouver
Xiao Z, Liu J, Cao X, Wang K, Li D, Liu Q. Time-Series Forecasting Method Based on Hierarchical Spatio-Temporal Attention Mechanism. Sensors. 2025;25(13):4001. doi:10.3390/s25134001
BibTeX
@article{Xiao2025,
author = {Xiao, Zhiguo and Liu, Junli and Cao, Xinyao and Wang, Ke and Li, Dongni and Liu, Qian},
title = {Time-Series Forecasting Method Based on Hierarchical Spatio-Temporal Attention Mechanism},
journal = {Sensors},
year = {2025},
volume = {25},
number = {13},
pages = {4001},
doi = {10.3390/s25134001}
}
EUVIMED